logD7.4 modeling using Bayesian regularized neural networks.: Assessment and correction of the errors of prediction

被引:54
作者
Bruneau, Pierre [1 ]
McElroy, Nathan R. [1 ]
机构
[1] AstraZeneca, F-51689 Reims 2, France
关键词
D O I
10.1021/ci0504014
中图分类号
R914 [药物化学];
学科分类号
100701 ;
摘要
Bayesian Regularized Neural Networks (BRNNs) employing Automatic Relevance Determination (ARD) are used to construct a predictive model for the distribution coefficient logD(7.4) from an in-house data set of 5000 compounds with experimental endpoints. A method for assessing the accuracy of prediction is established based upon a query compound's distance to the training set. logD(7.4) predictions are also dynamically corrected with an associated library of compounds of continuously updated, experimentally measured logD(7.4) values. A comparison of local models and associated libraries comprising separate ionization class subsets of compounds to compounds of a homogeneous ionization class reveals in this case that local models and libraries have no advantage over global models and libraries.
引用
收藏
页码:1379 / 1387
页数:9
相关论文
共 25 条
[21]  
Winkler D. A., 2004, DRUG DISCOV TODAY BI, V2, P104, DOI [DOI 10.1016/S1741-8364(04)02393-5, 10.1016/S1741-8364(04)02393-5]
[22]   Modelling blood-brain barrier partitioning using Bayesian neural nets [J].
Winkler, DA ;
Burden, FR .
JOURNAL OF MOLECULAR GRAPHICS & MODELLING, 2004, 22 (06) :499-505
[23]   Novel methods for the prediction of logP, pKa, and logD [J].
Xing, L ;
Glen, RC .
JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2002, 42 (04) :796-805
[24]   Dimension related distance and its application in QSAR/QSPR model error estimation [J].
Xu, YJ ;
Gao, H .
QSAR & COMBINATORIAL SCIENCE, 2003, 22 (04) :422-429
[25]  
YANG L, 2005, J CHEM INF COMPUT SC